Proactive Rejection and Grounded Execution: A Dual-Stage Intent Analysis Paradigm for Safe and Efficient AIoT Smart Homes

TL;DR

This paper introduces a dual-stage intent analysis framework for AIoT smart homes that improves safety and efficiency by filtering invalid commands and verifying physical feasibility before execution.

Contribution

It proposes a novel dual-stage intent-aware framework that separates high-level intent understanding from low-level physical verification, addressing reliability and interaction issues in AIoT systems.

Findings

Achieves 58.56% exact match rate, outperforming baselines by over 28%.

Reaches 87.04% rejection rate of invalid instructions.

Increases autonomous success rate from 42.86% to 71.43%.

Abstract

As Large Language Models (LLMs) transition from information providers to embodied agents in the Internet of Things (IoT), they face significant challenges regarding reliability and interaction efficiency. Direct execution of LLM-generated commands often leads to entity hallucinations (e.g., trying to control non-existent devices). Meanwhile, existing iterative frameworks (e.g., SAGE) suffer from the Interaction Frequency Dilemma, oscillating between reckless execution and excessive user questioning. To address these issues, we propose a Dual-Stage Intent-Aware (DS-IA) Framework. This framework separates high-level user intent understanding from low-level physical execution. Specifically, Stage 1 serves as a semantic firewall to filter out invalid instructions and resolve vague commands by checking the current state of the home. Stage 2 then employs a deterministic cascade verifier-a strict, step-by-step rule checker that verifies the room, device, and capability in sequence-to ensure the action is actually physically possible before execution. Extensive experiments on the HomeBench and SAGE benchmarks demonstrate that DS-IA achieves an Exact Match (EM) rate of 58.56% (outperforming baselines by over 28%) and improves the rejection rate of invalid instructions to 87.04%. Evaluations on the SAGE benchmark further reveal that DS-IA resolves the Interaction Frequency Dilemma by balancing proactive querying with state-based inference. Specifically, it boosts the Autonomous Success Rate (resolving tasks without unnecessary user intervention) from 42.86% to 71.43%, while maintaining high precision in identifying irreducible ambiguities that truly necessitate human clarification. These results underscore the framework's ability to minimize user disturbance through accurate environmental grounding.